Open to opportunities

Mahenth V

@mahenthv

Message

I build scalable Python backend services and evaluate LLMs through rigorous prompts, verifiers, and benchmarks.

India

Message

What I'm looking for

I'm looking to build scalable backend systems and contribute to LLM evaluation, prompt engineering, automated validation, and model benchmarking with collaborative international teams.

I'm currently building end-to-end LLM evaluation tasks at MillionLogics, including system prompts, grading rubrics, Python verifiers, adversarial test cases, and benchmark reference outputs. I evaluate models including Claude, GPT, Gemini, and Qwen for structured output, compliance, and failure patterns.

Previously, I enhanced multi-tenant CRM-ERP platforms at Slots Software Solutions using Python, Django, Django REST Framework, SQL, and microservices. I delivered REST APIs, secure OAuth2/JWT/RBAC authentication, asynchronous processing with Celery and Redis, and production deployments on AWS with Docker, Nginx, and GitHub Actions.

I've also led Django backend development at Qualde Digital Services, refactoring monolithic components into testable microservices and collaborating with distributed teams through Agile delivery, code reviews, and technical documentation.

Experience

Work history, roles, and key accomplishments

Current

Senior Python Developer

Current

MillionLogics

Nov 2025 - Present (9 months)

Performed comparative evaluation across frontier models including Claude, GPT, Gemini, and Qwen. Developed automated Python-based verifiers to validate LLM outputs against business rules and authored end-to-end evaluation tasks.